|Publication number||US4618984 A|
|Application number||US 06/502,415|
|Publication date||Oct 21, 1986|
|Filing date||Jun 8, 1983|
|Priority date||Jun 8, 1983|
|Also published as||CA1204865A, CA1204865A1, DE3467057D1, EP0128288A1, EP0128288B1|
|Publication number||06502415, 502415, US 4618984 A, US 4618984A, US-A-4618984, US4618984 A, US4618984A|
|Inventors||Subrata K. Das, Norman R. Dixon|
|Original Assignee||International Business Machines Corporation|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (10), Non-Patent Citations (6), Referenced by (102), Classifications (7), Legal Events (4)|
|External Links: USPTO, USPTO Assignment, Espacenet|
1. Field of the Invention
This invention relates to automatic discrete utterance voice recognition systems, and particularly relates to an adaptive automatic discrete utterance recognition system which requires only a prototype vocabulary set to be established by multiple repetition techniques and permits subsequent talkers to interact with the voice recognition system in adaptive mode in which mode the new talker is required merely to retrain the system for that limited subset of the vocabulary set in which the system cannot perform recognition.
2. Description of the Prior Art
Extant automatic discrete utterance voice recognition systems involve separate procedures for utterance prototype establishment in which multiple repetitions of each vocabulary item are taken from each talker. If a single repetition is taken the probability exists that the entire vocabulary prototype set will require re-establishment if an inappropriate prototype representation occurs.
Typical of such procedures--each talker repeating the prototype word list--are the following:
U.S. Pat. No. 3,333,248, Greenberg et al, SELF-ADAPTIVE SYSTEMS, July 25, 1967. Greenberg et al shows a self-adaptive pattern recognizer which, after initial training, may be switched to the operate mode and remains in operate mode until a character is presented which results in a reject signal. At this time the operator must assist by placing the identification switch in the position which corresponds to the rejected pattern, and the operator must determine whether the rejected pattern is a slightly modified one of the initial sample patterns or a new sample pattern and must set the appropriate switches including the switch to begin the training mode. In order to effectively update the self-adaptive circuit, a sufficient number of the initial sample patterns must be stored and represented to the self-adaptive circuit along with the rejected pattern.
U.S. Pat. No. 3,369,077, French et al, PITCH MODIFICATION OF AUDIO WAVEFORMS, Feb. 13, 1968. French et al shows a speech synthesizing system wherein pitch periods are adjusted according to a predetermined time base.
U.S. Pat. No. 3,440,617, Lesti et al, SIGNAL RESPONSIVE SYSTEMS, Apr. 22, 1969. Lesti et al shows a technique for recognition, independent of amplitude and duration of the signals to be recognized, by segmenting the signal into a series of component signals. The system extrapolates and interpolates inputs which it has never before received to the response which most closely resembles the signal. Data might be lost when it becomes replaced by new data. Lesti et al shows a technique in which newly coded samples are not discarded when the transmit buffer portion is already full but rather the oldest untransmitted coded sample is discarded to make room for storage of the new sample.
U.S. Pat. No. 3,665,450, Leban, METHOD AND MEANS FOR ENCODING AND DECODING IDEOGRAPHIC CHARACTERS, May 23, 1972. Leban shows a technique for handling ideographic characters.
U.S. Pat. No. 3,718,768, Abramson et al, VOICE OR ANALOG COMMUNICATION SYSTEM EMPLOYING ADAPTIVE ENCODING TECHNIQUES, Feb. 27, 1973. Abramson et al shows a technique for transmitting communications to remote stations which can detect their own identification signals and have their own sampling rates.
U.S. Pat. No. 4,069,393, Martin et al, WORD RECOGNITION APPARATUS AND METHOD, Jan. 17, 1978. Martin et al shows a technique for time normalizing training words and words for recognition. Martin et al deals with spoken input training words and generates a correlation function, and with feature extraction. During the training mode, the equipment is trained with new vocabulary words, preferably spoken by the person who is to later use the machine. It is desirable to use multiple samples of the same training word to obtain a faithful average sample.
U.S. Pat. No. 4,092,493, Rabiner et al, SPEECH RECOGNITION SYSTEM, May 30, 1978. Rabiner et al shows a speech recognition system in which test signals are time aligned to the average voiced interval of repetitions of each speech segment having a previously generated voiced interval linear prediction characteristic.
U.S. Pat. No. 4,297,528, Beno, TRAINING CIRCUIT FOR AUDIO SIGNAL RECOGNITION COMPUTER, Oct. 27, 1981. Beno shows a training circuit technique in which each training pattern, to be accepted for merging, must match the previously merged patterns by a threshold amount. The threshold is automatically varied as the number of previously merged training patterns increases.
C. C. Tappert, A PRELIMINARY INVESTIGATION OF ADAPTIVE CONTROL IN THE INTERACTION BETWEEN SEGMENTATION AND SEGMENT CLASSIFICATION IN AUTOMATIC RECOGNITION OF CONTINUOUS SPEECH, IEEE Trans. on Systems, Man, and Cybernetics, Vol. SMC2, No. 1, 1/72, pp. 6672. Tappert shows feedback control of the interaction of segmentation and segment classification in continuous speech recognition.
C. C. Tappert, et al, APPLICATION OF SEQUENTIAL DECODING FOR CONVERTING PHONETIC TO GRAPHIC REPRESENTATION IN AUTOMATIC RECOGNITION OF CONTINUOUS SPEECH (ARCS), IEEE Trans. on Audio and Electroacoustics, Vol. Au-21, No. 3, 6/73, pp. 225228. Tappert et al shows conversion of machine-contaminated phonetic descriptions of speaker performance into standard orthography. Distinction is made between speaker-and-machine-dependent corruption of phonetic input strings.
The invention provides an optimum technique for prototype establishment involving merely an initial single prototype statement of each vocabulary item (from the first talker or electronic equivalent) and thereafter requiring no recitation of vocabulary items by either the first or subsequent talkers--except for those vocabulary items in which the system has difficulty performing correct recognition. Retraining for such misrecognized vocabulary items is integrated with the recognition procedure.
The object of the invention is to provide inexpensive, fast, unobtrusive adaptation of a speech recognition system for the special requirements of each talker.
Another object of the invention is that the talker should not be very aware that the system is being retrained.
Another object of the invention is for the system to provide prompts to lead the talker through the limited subset of the vocabulary prototype set in as unobtrusive a manner as possible and within the talker's context.
Another object of the invention is to provide system retraining only for that limited subset of the vocabulary prototype set in which both of the following occur:
(1) the talker utters a word from the prototype set; and
(2) the system has difficulty performing recognition of the word spoken.
This permits the system to avoid retraining for those words which are not used.
FIG. 1 is a block diagram of the adaptive automatic discrete utterance recognition system of the invention. Of the system shown, the portion of FIG. 1 most significant to the invention is the subsystem box marked "Adaptive Training."
FIG. 2 is a detailed diagram of the Adaptive Training subsystem.
FIG. 1 is a block diagram of the adaptive automatic discrete utterance recognition system of the invention. Note that prior art voice recognition systems generally require each new talker to provide a multiple recitation of the prototype vocabulary for subsequent recognition. If for any reason a talker needed to change the prototype vocabulary (e.g., if the talker developed a respiratory problem) the original procedure required repetition in its entirety. This invention eliminates, even for the first talker, the need for multiple recitation of the prototype vocabulary, and eliminates the need for any recitation at all of the entire prototype vocabulary by any talker. Only if the system should have difficulty performing recognition of any individual vocabulary item is the talker prompted to utter that individual vocabulary item.
The method of this invention requires the following operational modes:
Mode 1 Initializing Mode
A selected prototypical talker recites one prototype vocabulary keyword utterance for each of a prototype set of vocabulary items, the system converting each prototype vocabulary keyword utterance to a code pattern for subsequent use in recognition procedures. Where appropriate, a prototype set may be calculated and entered in coded form without any recitation by any talker at all.
Mode 2 Normal Operation Mode
A talker (which talker may be the prototypical talker or a subsequent talker) provides voice input for recognition by the system so long as recognition proceeds satisfactorily. (Under conditions not including consistent recognition errors no further vocabulary training occurs.)
Mode 3 Adaptive Retraining Mode
Upon conditions of consistent recognition error for a sample vocabulary item, the system prompts the talker as required for adaptive retraining.
Details of the method will be subsequently discussed under the heading "INVENTIVE METHOD."
FIG. 1 shows the adaptive automatic discrete utterance recognition system of the invention. Host computer 1 is connected to user interface 2, which in turn connects to display unit 3, microphone 4 and loudspeaker 5. User interface 2 provides the proper interface for the user and the recognition system, which may take a number of forms such as that shown. In the form shown in FIG. 1, user data passes via line 6 to signal analysis and feature abstraction unit 7 for distribution of original training patterns (prototypes) along pathway 8 to prototype storage 9 during training mode--and during recognition mode, feature patterns pass along pathway 10 to pattern recognition unit 11. Information of a control nature passes between pattern recognition unit 11 and prototype storage 9 via pathway 12; prototype patterns for recognition are supplied to pattern recognition mechanism 11 along pathway 13. Recognition information, in the form of utterance identification distance values, is provided via pathway 14 to decision mechanism 15. Recognition result data passes via pathway 16 back to user interface 2 for action.
Decision information also passes between decision mechanism 15 and adaptive training unit 20 via pathways 17 and 18, and from adaptive training unit 16 to prototype storage 9 via pathway 19. As previously pointed out, the portion of FIG. 1 most significant to the invention is the subsystem (identified by reference character 20) marked "Adaptive Training." Nodes (1), (2) and (3) are shown in FIG. 1 for ease in relating FIG. 1 with FIG. 2.
FIG. 2 is a detailed diagram of the Adaptive Training subsystem 20 of FIG. 1. Keyword unit 21 determines whether or not the utterance is a keyword. If "no," a notification is forwarded via pathway 22 to node (2), which connects to pathway 18 in both FIGS. 1 and 2. If "yes,38 a notification is forwarded to incrementer 23 via "YES" line 24 to prompt a user identification of the keyword by a sequence of choice numbers. Incrementer 23 increments the current keyword choice number and provides the next choice number to mechanism 25 for determination whether the keyword choice number is equal to the current choice. If the choice number is not the appropriate choice number, the choice prompts continue by a signal to maximum identification mechanism 26 (CHOICE NO=CHMAX?) for continuing through the list of choices. If the choice number is less than maximum, a signal on "NO38 pathway 28 controls a prompt for the next choice number. When the last choice number is reached, CHOICE NO=CHMAX box 26 signals "YES" via pathway 29 to invoke REPEAT ENTRY mechanism 30 for a new list of choices.
Once the utterance choice number is determined, as identified by "YES" pathway 31 to PROMPT CHOICE box 32, the user is provided with a prompt requesting that the user make the utterance of choice. This utterance is the utterance to be used in certain situations as the new prototype.
The utterance is processed according to the processing technique selected for the utterance recognition system, and coded as utterance code INPUT 1. The prompt requires a second utterance, which is processed and coded as utterance code INPUT 2. These utterance code inputs are provided, along with a similarly coded prototype utterance, to three matrix comparators 33, 34 and 35, which make distance comparisons for the three codes. Matrix comparator 33 provides distance code Dl relating the two new input utterances to each other. Matrix comparator 34 provides distance code D2 relating the prototype and the second new input utterance to each other. Matrix comparator 35 provides distance code D3 relating the prototype and the first new input utterance to each other. The distance codes are compared by comparators 36 and 37. The function desired is to replace the prototype utterance by the utterance INPUT 2 where it is determined that INPUT 1 and INPUT 2 differ less from each other than they do from the prototype. If comparator 36 determines that INPUT 2 is closer to the prototype than to INPUT 1 (Dl is NOT less than D2) then mechanism 36 transmits on "NO" pathway 38 to Node (2) in FIG. 1, signalling the decision mechanism to go on without altering the prototype. Similarly, if comparator 37 determines that INPUT 1 is closer to the prototype than to INPUT 2 (Dl is NOT less than D3) then mechanism 37 transmits on "NO" line 38 to Node (2) in FIG. 1, signalling the decision mechanism to go on without altering the prototype.
The function desired is to alter the prototype when D1 is less than D2 and D1 is also less than D3. Comparator 37 provides a "YES" output on line 39 to initiate PROTOTYPE=INPUT 2 action from mechanism 40. Signal line 19 at Node (3) in FIG. 1 controls the action of replacing the prototype vocabulary entry with INPUT 2.
This adaptive replacement of the prototype vocabulary entry as a function of the determination that the new utterance is acceptable permits a prototype vocabulary to be established once, then used insofar as acceptable, with unobtrusive adaptive alteration of a limited number of vocabulary words as they appear in the context of normal operation. When the prototype word is misrecognized for any reason (dialect, pronunciation or other difference between speakers--or change in delivery by the same talker), this system identifies the misrecognition, prompts a twin input of the utterance, compares the inputs to each other and to the prototype, and in the situation where it is determined that the inputs fulfill the criteria, replace the prototype with one of the new inputs.
FIG. 2 details the procedures for adaptive retraining of prototype vocabulary items. During the recognition process if the talker produces a keyword mistake the adaptive retraining routine is invoked. Under computer control the procedures are entered and a stack of vocabulary item choices--related to the words just before the keyword mistake recognition--is sent to the adaptive training stage. Using this stack the system prompts the user to indicate which stack vocabulary item was uttered just prior to its identification as an unrecognized utterance. (This prompting can either be by audio response or character display from a gas panel, cathode ray tube, or the like.) If the word equivalent to the misrecognized utterance is not contained in the stack, the user is prompted to recite the utterance again, and the recognition procedure continues. Upon acknowledgment by the talker that a stack vocabulary item matches the utterance (INPUT 1), the user is prompted to provide a new prototype keyword candidate (INPUT 2) appropriate to that vocabulary item. The system calculates the matrix distances [INPUT 1 vs. INPUT 2=(D1)], [PROTOTYPE vs. INPUT 2=(D2)], and [PROTOTYPE vs. INPUT 1=(D3)], where INPUT 1 is the misrecognized utterance and INPUT 2 is the prompted utterance of the same keyword. If D1 is less than D2, and if D1 is less than D3, then INPUT 2 becomes the new prototype keyword. Otherwise the old prototype is retained. This procedure guarantees the best currently available prototype relative to the current user's (the user's current) speech characteristics. This procedure is independent of the mode of determining the particular matrix distance characteristics employed in the recognition process.
The following steps are followed:
1. Prototypical talker recites the keyword set, which keyword set is stored in coded form as the prototype vocabulary keyword set. Alternatively, the prototype vocabulary keyword set may be calculated and stored.
2. A subsequent talker utters a sample keyword for recognition.
3. If recognition occurs, proceed.
4. If recognition fails, enter adaptive retraining routine.
5. Set adaptive training stage with stack of recognition choice words related to the misrecognized keyword.
6. Prompt user to indicate which word of the stack was intended.
7. Check whether misrecognized keyword is in stack.
8. If 7 is negative, prompt talker to repeat misrecognized keyword.
9. Proceed with recognition procedure.
10. If 7 is positive, prompt talker to utter a new prototype candidate.
11. Calculate matrix distances:
INPUT 1 vs. INPUT 2=(D1)
PROT vs. INPUT 2=(D2).
PROT vs. INPUT 1=(D3), 12. Compare D1, D2, D3.
13. If D1<D2 AND Dl<D3, then select INPUT 2 as new prototype and proceed.
The inventive method may be performed according to a number of variations without departing from the spirit and scope of the adaptive automatic discrete utterance recognition technique of this patent specification as pointed out in the following claims.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US3333248 *||Dec 20, 1963||Jul 25, 1967||Ibm||Self-adaptive systems|
|US3369077 *||Jun 9, 1964||Feb 13, 1968||Ibm||Pitch modification of audio waveforms|
|US3440617 *||Mar 31, 1967||Apr 22, 1969||Andromeda Inc||Signal responsive systems|
|US3665450 *||Jul 2, 1968||May 23, 1972||Leo Stanger||Method and means for encoding and decoding ideographic characters|
|US3718768 *||Aug 9, 1971||Feb 27, 1973||Adaptive Tech||Voice or analog communication system employing adaptive encoding techniques|
|US4069393 *||Dec 11, 1974||Jan 17, 1978||Threshold Technology, Inc.||Word recognition apparatus and method|
|US4092493 *||Nov 30, 1976||May 30, 1978||Bell Telephone Laboratories, Incorporated||Speech recognition system|
|US4297528 *||Sep 10, 1979||Oct 27, 1981||Interstate Electronics Corp.||Training circuit for audio signal recognition computer|
|DE2945377A1 *||Nov 9, 1979||May 22, 1980||Hajime Industries||Verfahren zur untersuchung von mustern|
|GB2098773A *||Title not available|
|1||C. C. Tappert et al., "Application of Sequential Decoding for Converting Phoenetic to Graphic Representation in Automatic Recognition of Continuous Speech (ARCS)," IEEE Trans. on Audio and Electroacoustics, vol. Au-21, No. 3, 6/73, pp. 225-228.|
|2||*||C. C. Tappert et al., Application of Sequential Decoding for Converting Phoenetic to Graphic Representation in Automatic Recognition of Continuous Speech (ARCS), IEEE Trans. on Audio and Electroacoustics, vol. Au 21, No. 3, 6/73, pp. 225 228.|
|3||C. C. Tappert, "A Preliminary Investigation of Adaptive Control in the Interaction Between Segmentation and Segment Classification in Automatic Recognition of Continuous Speech," IEEE Trans. on Systems, Man, and Cybernetics, vol. SMC2, No. 1, 1/72, pp. 66-72.|
|4||*||C. C. Tappert, A Preliminary Investigation of Adaptive Control in the Interaction Between Segmentation and Segment Classification in Automatic Recognition of Continuous Speech, IEEE Trans. on Systems, Man, and Cybernetics, vol. SMC2, No. 1, 1/72, pp. 66 72.|
|5||*||Proceedings of the Fourth International Joint Conference on Pattern Recognition, Nov. 7th 10th 1978, Kyoto, JP, pp. 985 989, IEEE, New York, US; Sei ichi Nakagawa et al.: A Real Time Spoken Word Recognition System in a Large Vocabulary with Learning Capability of Speaker Differences .|
|6||Proceedings of the Fourth International Joint Conference on Pattern Recognition, Nov. 7th-10th 1978, Kyoto, JP, pp. 985-989, IEEE, New York, US; Sei-ichi Nakagawa et al.: "A Real Time Spoken Word Recognition System in a Large Vocabulary with Learning Capability of Speaker Differences".|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US4783802 *||Sep 12, 1985||Nov 8, 1988||Kabushiki Kaisha Toshiba||Learning system of dictionary for speech recognition|
|US4797927 *||Oct 30, 1985||Jan 10, 1989||Grumman Aerospace Corporation||Voice recognition process utilizing content addressable memory|
|US4908864 *||Apr 2, 1987||Mar 13, 1990||Sharp Kabushiki Kaisha||Voice recognition method and apparatus by updating reference patterns|
|US4972485 *||May 23, 1989||Nov 20, 1990||At&T Bell Laboratories||Speaker-trained speech recognizer having the capability of detecting confusingly similar vocabulary words|
|US4991216 *||Mar 23, 1990||Feb 5, 1991||Matsushita Electric Industrial Co., Ltd.||Method for speech recognition|
|US5033088 *||Dec 21, 1989||Jul 16, 1991||Voice Processing Corp.||Method and apparatus for effectively receiving voice input to a voice recognition system|
|US5072452 *||Nov 2, 1989||Dec 10, 1991||International Business Machines Corporation||Automatic determination of labels and Markov word models in a speech recognition system|
|US5123049 *||Apr 11, 1990||Jun 16, 1992||Kabushiki Kaisha Toshiba||Pattern recognition apparatus with retrieval reference patterns|
|US5127055 *||Feb 11, 1991||Jun 30, 1992||Kurzweil Applied Intelligence, Inc.||Speech recognition apparatus & method having dynamic reference pattern adaptation|
|US5131043 *||Nov 20, 1989||Jul 14, 1992||Matsushita Electric Industrial Co., Ltd.||Method of and apparatus for speech recognition wherein decisions are made based on phonemes|
|US5146502 *||Feb 26, 1990||Sep 8, 1992||Davis, Van Nortwick & Company||Speech pattern correction device for deaf and voice-impaired|
|US5146503 *||Aug 24, 1988||Sep 8, 1992||British Telecommunications Public Limited Company||Speech recognition|
|US5150449 *||Apr 23, 1991||Sep 22, 1992||Nec Corporation||Speech recognition apparatus of speaker adaptation type|
|US5212821 *||Mar 29, 1991||May 18, 1993||At&T Bell Laboratories||Machine-based learning system|
|US5251283 *||Dec 4, 1989||Oct 5, 1993||U.S. Philips Corporation||Speech recognition system with an automatic adaptive learning device|
|US5315689 *||Dec 21, 1992||May 24, 1994||Kabushiki Kaisha Toshiba||Speech recognition system having word-based and phoneme-based recognition means|
|US5377301 *||Jan 21, 1994||Dec 27, 1994||At&T Corp.||Technique for modifying reference vector quantized speech feature signals|
|US5613036 *||Apr 25, 1995||Mar 18, 1997||Apple Computer, Inc.||Dynamic categories for a speech recognition system|
|US5737724 *||Aug 8, 1996||Apr 7, 1998||Lucent Technologies Inc.||Speech recognition employing a permissive recognition criterion for a repeated phrase utterance|
|US5758322 *||Dec 9, 1994||May 26, 1998||International Voice Register, Inc.||Method and apparatus for conducting point-of-sale transactions using voice recognition|
|US5797116 *||Jan 21, 1997||Aug 18, 1998||Canon Kabushiki Kaisha||Method and apparatus for recognizing previously unrecognized speech by requesting a predicted-category-related domain-dictionary-linking word|
|US5799279 *||Nov 13, 1995||Aug 25, 1998||Dragon Systems, Inc.||Continuous speech recognition of text and commands|
|US5829000 *||Oct 31, 1996||Oct 27, 1998||Microsoft Corporation||Method and system for correcting misrecognized spoken words or phrases|
|US5852801 *||Oct 4, 1995||Dec 22, 1998||Apple Computer, Inc.||Method and apparatus for automatically invoking a new word module for unrecognized user input|
|US5852804 *||Apr 11, 1997||Dec 22, 1998||Fujitsu Limited||Method and apparatus for speech recognition|
|US5884258 *||Oct 31, 1996||Mar 16, 1999||Microsoft Corporation||Method and system for editing phrases during continuous speech recognition|
|US5899976 *||Oct 31, 1996||May 4, 1999||Microsoft Corporation||Method and system for buffering recognized words during speech recognition|
|US5903864 *||Nov 13, 1995||May 11, 1999||Dragon Systems||Speech recognition|
|US5915238 *||Jul 16, 1996||Jun 22, 1999||Tjaden; Gary S.||Personalized audio information delivery system|
|US5950160 *||Oct 31, 1996||Sep 7, 1999||Microsoft Corporation||Method and system for displaying a variable number of alternative words during speech recognition|
|US5960395 *||Feb 6, 1997||Sep 28, 1999||Canon Kabushiki Kaisha||Pattern matching method, apparatus and computer readable memory medium for speech recognition using dynamic programming|
|US6012027 *||Sep 17, 1997||Jan 4, 2000||Ameritech Corporation||Criteria for usable repetitions of an utterance during speech reference enrollment|
|US6088671 *||Jun 17, 1998||Jul 11, 2000||Dragon Systems||Continuous speech recognition of text and commands|
|US6163768 *||Jun 15, 1998||Dec 19, 2000||Dragon Systems, Inc.||Non-interactive enrollment in speech recognition|
|US6212498||Mar 28, 1997||Apr 3, 2001||Dragon Systems, Inc.||Enrollment in speech recognition|
|US6212499 *||Sep 23, 1999||Apr 3, 2001||Canon Kabushiki Kaisha||Audible language recognition by successive vocabulary reduction|
|US6275799 *||Feb 2, 1995||Aug 14, 2001||Nec Corporation||Reference pattern learning system|
|US6278771 *||Apr 30, 1999||Aug 21, 2001||Ameritech Corporation||Method and system for providing enhanced call waiting with verification and name change service|
|US6311157||Dec 31, 1992||Oct 30, 2001||Apple Computer, Inc.||Assigning meanings to utterances in a speech recognition system|
|US6424943||Jul 24, 2000||Jul 23, 2002||Scansoft, Inc.||Non-interactive enrollment in speech recognition|
|US6487530 *||Mar 30, 1999||Nov 26, 2002||Nortel Networks Limited||Method for recognizing non-standard and standard speech by speaker independent and speaker dependent word models|
|US6704710||Oct 12, 2001||Mar 9, 2004||Apple Computer, Inc.||Assigning meanings to utterances in a speech recognition system|
|US6732074 *||Jan 27, 2000||May 4, 2004||Ricoh Company, Ltd.||Device for speech recognition with dictionary updating|
|US6775357 *||Jul 9, 2001||Aug 10, 2004||Sbc Properties, L.P.||Method and system for providing enhanced call waiting with verification and name change service|
|US6799162 *||Dec 15, 1999||Sep 28, 2004||Sony Corporation||Semi-supervised speaker adaptation|
|US6873951 *||Sep 29, 2000||Mar 29, 2005||Nortel Networks Limited||Speech recognition system and method permitting user customization|
|US7003465 *||Oct 12, 2001||Feb 21, 2006||Matsushita Electric Industrial Co., Ltd.||Method for speech recognition, apparatus for the same, and voice controller|
|US7062435||Jul 26, 1999||Jun 13, 2006||Canon Kabushiki Kaisha||Apparatus, method and computer readable memory medium for speech recognition using dynamic programming|
|US7099441 *||Jun 17, 2004||Aug 29, 2006||Sbc Properties, L.P.||Method and system for providing enhanced call waiting with verification and name change service|
|US7127394||Feb 18, 2004||Oct 24, 2006||Apple Computer, Inc.||Assigning meanings to utterances in a speech recognition system|
|US7319956 *||Mar 23, 2001||Jan 15, 2008||Sbc Properties, L.P.||Method and apparatus to perform speech reference enrollment based on input speech characteristics|
|US7409046||Jul 19, 2006||Aug 5, 2008||At&T Knowledge Ventures, L.P.||Method and system for providing enhanced call waiting with verification and name change service|
|US7478037||Oct 13, 2006||Jan 13, 2009||Apple Inc.||Assigning meanings to utterances in a speech recognition system|
|US7630895||Jan 12, 2005||Dec 8, 2009||At&T Intellectual Property I, L.P.||Speaker verification method|
|US7966176 *||Oct 22, 2009||Jun 21, 2011||At&T Intellectual Property I, L.P.||System and method for independently recognizing and selecting actions and objects in a speech recognition system|
|US8751232||Feb 6, 2013||Jun 10, 2014||At&T Intellectual Property I, L.P.||System and method for targeted tuning of a speech recognition system|
|US8824659||Jul 3, 2013||Sep 2, 2014||At&T Intellectual Property I, L.P.||System and method for speech-enabled call routing|
|US8892446||Dec 21, 2012||Nov 18, 2014||Apple Inc.||Service orchestration for intelligent automated assistant|
|US8903716||Dec 21, 2012||Dec 2, 2014||Apple Inc.||Personalized vocabulary for digital assistant|
|US8930191||Mar 4, 2013||Jan 6, 2015||Apple Inc.||Paraphrasing of user requests and results by automated digital assistant|
|US8942986||Dec 21, 2012||Jan 27, 2015||Apple Inc.||Determining user intent based on ontologies of domains|
|US8977584||Jan 25, 2011||Mar 10, 2015||Newvaluexchange Global Ai Llp||Apparatuses, methods and systems for a digital conversation management platform|
|US9088652||Jul 1, 2014||Jul 21, 2015||At&T Intellectual Property I, L.P.||System and method for speech-enabled call routing|
|US9112972||Oct 4, 2012||Aug 18, 2015||Interactions Llc||System and method for processing speech|
|US9117447||Dec 21, 2012||Aug 25, 2015||Apple Inc.||Using event alert text as input to an automated assistant|
|US9262612||Mar 21, 2011||Feb 16, 2016||Apple Inc.||Device access using voice authentication|
|US9300784||Jun 13, 2014||Mar 29, 2016||Apple Inc.||System and method for emergency calls initiated by voice command|
|US9318108||Jan 10, 2011||Apr 19, 2016||Apple Inc.||Intelligent automated assistant|
|US9330720||Apr 2, 2008||May 3, 2016||Apple Inc.||Methods and apparatus for altering audio output signals|
|US9338493||Sep 26, 2014||May 10, 2016||Apple Inc.||Intelligent automated assistant for TV user interactions|
|US9350862||Jul 10, 2015||May 24, 2016||Interactions Llc||System and method for processing speech|
|US9368111||Apr 25, 2014||Jun 14, 2016||Interactions Llc||System and method for targeted tuning of a speech recognition system|
|US9368114||Mar 6, 2014||Jun 14, 2016||Apple Inc.||Context-sensitive handling of interruptions|
|US9424861||May 28, 2014||Aug 23, 2016||Newvaluexchange Ltd||Apparatuses, methods and systems for a digital conversation management platform|
|US9424862||Dec 2, 2014||Aug 23, 2016||Newvaluexchange Ltd||Apparatuses, methods and systems for a digital conversation management platform|
|US9430463||Sep 30, 2014||Aug 30, 2016||Apple Inc.||Exemplar-based natural language processing|
|US9431028||May 28, 2014||Aug 30, 2016||Newvaluexchange Ltd||Apparatuses, methods and systems for a digital conversation management platform|
|US9483461||Mar 6, 2012||Nov 1, 2016||Apple Inc.||Handling speech synthesis of content for multiple languages|
|US9495129||Mar 12, 2013||Nov 15, 2016||Apple Inc.||Device, method, and user interface for voice-activated navigation and browsing of a document|
|US9502031||Sep 23, 2014||Nov 22, 2016||Apple Inc.||Method for supporting dynamic grammars in WFST-based ASR|
|US9535906||Jun 17, 2015||Jan 3, 2017||Apple Inc.||Mobile device having human language translation capability with positional feedback|
|US9548050||Jun 9, 2012||Jan 17, 2017||Apple Inc.||Intelligent automated assistant|
|US20020032566 *||Jul 26, 1999||Mar 14, 2002||Eli Tzirkel-Hancock||Apparatus, method and computer readable memory medium for speech recogniton using dynamic programming|
|US20020133343 *||Oct 12, 2001||Sep 19, 2002||Keiko Morii||Method for speech recognition, apparatus for the same, and voice controller|
|US20030061030 *||Sep 20, 2002||Mar 27, 2003||Canon Kabushiki Kaisha||Natural language processing apparatus, its control method, and program|
|US20040148169 *||Jan 23, 2003||Jul 29, 2004||Aurilab, Llc||Speech recognition with shadow modeling|
|US20040162729 *||Feb 18, 2004||Aug 19, 2004||Strong Robert Don||Assigning meanings to utterances in a speech recognition system|
|US20050013420 *||Jun 17, 2004||Jan 20, 2005||Sbc Properties, L.P.||Method and system for providing enhanced call waiting with verification and name change service|
|US20050036589 *||Mar 23, 2001||Feb 17, 2005||Ameritech Corporation||Speech reference enrollment method|
|US20050143996 *||Jan 12, 2005||Jun 30, 2005||Bossemeyer Robert W.Jr.||Speaker verification method|
|US20060256936 *||Jul 19, 2006||Nov 16, 2006||Sbc Properties, L.P.||Method and system for providing enhanced call waiting with verification and name change service|
|US20070033038 *||Oct 13, 2006||Feb 8, 2007||Strong Robert D||Assigning meanings to utterances in a speech recognition system|
|US20080071538 *||Nov 20, 2007||Mar 20, 2008||Bossemeyer Robert Wesley Jr||Speaker verification method|
|EP1069551A2 *||Jun 6, 2000||Jan 17, 2001||Bayerische Motoren Werke Aktiengesellschaft||Speech recognition system and method for recognising given speech patterns, specially for voice control|
|EP1069551A3 *||Jun 6, 2000||May 23, 2001||Bayerische Motoren Werke Aktiengesellschaft||Speech recognition system and method for recognising given speech patterns, specially for voice control|
|EP1239461A1 *||Mar 6, 2001||Sep 11, 2002||Siemens Aktiengesellschaft||Speech recognition method|
|WO1987002817A1 *||Oct 30, 1986||May 7, 1987||Grumman Aerospace Corporation||Voice recognition process utilizing content addressable memory|
|WO1998002873A1 *||Jul 14, 1997||Jan 22, 1998||Tjaden Gary S||Personalized audio information delivery system|
|WO1999013456A1 *||Aug 17, 1998||Mar 18, 1999||Ameritech Corporation||Speech reference enrollment method|
|WO2000067455A1 *||Apr 18, 2000||Nov 9, 2000||Ameritech Corporation||Method and system for providing enhanced call waiting with verification and name change service|
|WO2004066267A2 *||Jan 21, 2004||Aug 5, 2004||Aurilab, Llc||Speech recognition with existing and alternative models|
|WO2004066267A3 *||Jan 21, 2004||Dec 9, 2004||Aurilab Llc||Speech recognition with existing and alternative models|
|U.S. Classification||704/244, 704/E15.011, 704/246|
|International Classification||G10L15/06, G10L11/00|
|Jun 8, 1983||AS||Assignment|
Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, ARMON
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST.;ASSIGNORS:DAS, SUBRATA K.;DIXON, NORMAN R.;REEL/FRAME:004205/0664
Effective date: 19830602
|Jan 18, 1990||FPAY||Fee payment|
Year of fee payment: 4
|Jan 24, 1994||FPAY||Fee payment|
Year of fee payment: 8
|Jan 5, 1998||FPAY||Fee payment|
Year of fee payment: 12